LIFESTYLE RISK ASSESSMENT OF TYPE 2 DIABETES USING MACHINE LEARNING

The rising global prevalence of Type 2 Diabetes Mellitus (T2DM) underscores the urgent need for proactive risk assessment strategies, especially those leveraging advancements in artificial intelligence. This study presents the design and implementation of a machine learning-based system for lifestyle risk assessment of Type 2 diabetes. The project aims to predict individuals' susceptibility to T2DM based on lifestyle factors such as diet, physical activity, smoking habits, and body mass index, using supervised learning algorithms. Data was gathered and collected through questionaire, capturing key health and behavioral indicators The data was preprocessed and analyzed through exploratory data analysis (EDA) and feature engineering techniques to enhance predictive power. Multiple classification algorithms such as Logistic Regression, Random Forest, and Support Vector Machine were trained and evaluated using standard performance metrics including accuracy, precision, recall, and F1-score. The user interface was built using a Streamlit framework, allowing users to input their lifestyle details and receive personalized diabetes risk predictions in real-time. This system not only demonstrates the potential of machine learning in preventive healthcare but also serves as a practical tool for promoting awareness and encouraging positive lifestyle changes to reduce the risk of developing Type 2 diabetes.